Zonglong Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zonglong Bai has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
Jinwei Sun
School of Instrument Science and Engineering, Harbin Institute of Technology, Harbin, China
6 shared publications- Junyan Zhang
North China Electric Power University
4 shared publications Liming Shi
Chongqing Univ Posts & Telecommun, Comunicat & Informat Engn, Chongqing 400065, Peoples R China
3 shared publications- Mads Græsbøll Christensen
Audio Analysis Lab, Department of Electronic Systems, Aalborg University, Aalborg, Denmark
3 shared publications - Wenzhao Zhu
Key Laboratory of Intelligent Control and Neural Information Processing, Education Ministry of China, Yanshan University, Qinhuangdao 066004, China
3 shared publications - Zhiyuan Xie
North China Electric Power University
3 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2026 (1) , 9918106
A Super Augmented Nested Array With L‐Shaped Geometry for Enhanced Two‐Dimensional DOA Estimation
This study proposes an L‐shaped super augmented nested array (LSANA) structure for two‐dimensional (2‐D) direction of arrival (DOA) estimation. The proposed LSANA structure consists of two linear arrays located along the x ‐axis and y ‐axis, respectively. Each linear array is a SANA that achieves lower mutual coupling (MC) and higher degrees of freedom (DOF). The azimuth and elevation angles are estimated separately for each part of the array, and then the pairing of these angles is achieved using the cross‐covariance matrices of the respective data sections, thus enabling 2‐D DOA estimation. Finally, through simulation experiments, the proposed LSANA is compared with other sparse array structures. The results indicate that the proposed LSANA can achieve higher DOF with lower MC, while also providing improved estimation accuracy for DOA.
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2026 (1) , 9918106
Open AccessA Super Augmented Nested Array With L‐Shaped Geometry for Enhanced Two‐Dimensional DOA Estimation
This study proposes an L‐shaped super augmented nested array (LSANA) structure for two‐dimensional (2‐D) direction of arrival (DOA) estimation. The proposed LSANA structure consists of two linear arrays located along the x ‐axis and y ‐axis, respectively. Each linear array is a SANA that achieves lower mutual coupling (MC) and higher degrees of freedom (DOF). The azimuth and elevation angles are estimated separately for each part of the array, and then the pairing of these angles is achieved using the cross‐covariance matrices of the respective data sections, thus enabling 2‐D DOA estimation. Finally, through simulation experiments, the proposed LSANA is compared with other sparse array structures. The results indicate that the proposed LSANA can achieve higher DOF with lower MC, while also providing improved estimation accuracy for DOA.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 9703617
Extended Multiarm Nested Array Structure for 2-D DOA Estimation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 9703617
Extended Multiarm Nested Array Structure for 2-D DOA Estimation
- Open Access
A New Hybrid Adaptive Self-Loading Filter and GRU-Net for Active Noise Control in a Right-Angle Bending Pipe of an Air Conditioner
The air-conditioner noise in a rehabilitation room can seriously affect the mental state of patients. However, the existing single-layer active noise control (ANC) filters may fail to attenuate the complicated harmonic noise, and the deep recursive ANC method may fail to work in real time. To solve the problem, in a bending-pipe model, a new hybrid adaptive self-loading filtered-x least-mean-square (ASL-FxLMS) and convolutional neural network-gate recurrent unit (CNN-GRU) network is proposed. At first, based on the recursive GRU translation core, an improved CNN-GRU network with multi-head attention layers is proposed. Especially for complicated harmonic noises with more or fewer frequencies than harmonic models, the attenuation performance will be improved. In addition, its structure is optimized to decrease the computing load. In addition, an improved time-delay estimator is applied to improve the real-time ANC performance of CNN-GRU. Meanwhile, an adaptive self-loading FxLMS algorithm has been developed to deal with the uncertain components of complicated harmonic noise. Moreover, to achieve balance attenuation, robustness, and tracking performance, the ASL-FxLMS and CNN-GRU are connected by a convex combination structure. Furthermore, theoretical analysis and simulations are also conducted to show the effectiveness of the proposed method.
Open AccessA New Hybrid Adaptive Self-Loading Filter and GRU-Net for Active Noise Control in a Right-Angle Bending Pipe of an Air Conditioner
The air-conditioner noise in a rehabilitation room can seriously affect the mental state of patients. However, the existing single-layer active noise control (ANC) filters may fail to attenuate the complicated harmonic noise, and the deep recursive ANC method may fail to work in real time. To solve the problem, in a bending-pipe model, a new hybrid adaptive self-loading filtered-x least-mean-square (ASL-FxLMS) and convolutional neural network-gate recurrent unit (CNN-GRU) network is proposed. At first, based on the recursive GRU translation core, an improved CNN-GRU network with multi-head attention layers is proposed. Especially for complicated harmonic noises with more or fewer frequencies than harmonic models, the attenuation performance will be improved. In addition, its structure is optimized to decrease the computing load. In addition, an improved time-delay estimator is applied to improve the real-time ANC performance of CNN-GRU. Meanwhile, an adaptive self-loading FxLMS algorithm has been developed to deal with the uncertain components of complicated harmonic noise. Moreover, to achieve balance attenuation, robustness, and tracking performance, the ASL-FxLMS and CNN-GRU are connected by a convex combination structure. Furthermore, theoretical analysis and simulations are also conducted to show the effectiveness of the proposed method.
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (15) , 29492-29508
A New Adaptive Sound Zone Strategy-Based Hybrid FxNLMS and CNN-LSTM Network for Multichannel Active Noise Control in a Rehabilitation Room
The equipment in the rehabilitation room can generate noise, affecting patients’ emotions and delaying their recovery. To create a quiet area in the rehabilitation room, a new adaptive sound zone strategy-based hybrid adaptive filter and deep learning network for a multi-channel active noise control (ANC) system is proposed. Firstly, to enhance the attenuation level in critical areas and achieve better robustness, a novel sound zone control strategy is integrated into the cost function of the proposed multi-channel ANC algorithm. Then, an improved hybrid filtered-x normalized least mean square (FxNLMS) and convolutional neural network-based long-short-term memory (CNN-LSTM) is utilized instead of a single adaptive filter to reduce time-varying and long-term periodic noise. In addition, a new phase-tracking filter is employed to assist the CNN-LSTM in enhancing its phase-tracking ability. Moreover, the proposed hybrid FxNLMS and CNN-LSTM multi-channel network is more effective at attenuating time-varying noise than the conventional single filter network. Meanwhile, it offers superior noise reduction and real-time tracking performance compared to the deep ANC network. And compared to the conventional delay compensation method, the proposed phase tracking filter demonstrates a smaller statistical average phase error. Furthermore, simulations using recorded noise in a rehabilitation room model illustrate the efficiency of the proposed method.
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (15) , 29492-29508
A New Adaptive Sound Zone Strategy-Based Hybrid FxNLMS and CNN-LSTM Network for Multichannel Active Noise Control in a Rehabilitation Room
The equipment in the rehabilitation room can generate noise, affecting patients’ emotions and delaying their recovery. To create a quiet area in the rehabilitation room, a new adaptive sound zone strategy-based hybrid adaptive filter and deep learning network for a multi-channel active noise control (ANC) system is proposed. Firstly, to enhance the attenuation level in critical areas and achieve better robustness, a novel sound zone control strategy is integrated into the cost function of the proposed multi-channel ANC algorithm. Then, an improved hybrid filtered-x normalized least mean square (FxNLMS) and convolutional neural network-based long-short-term memory (CNN-LSTM) is utilized instead of a single adaptive filter to reduce time-varying and long-term periodic noise. In addition, a new phase-tracking filter is employed to assist the CNN-LSTM in enhancing its phase-tracking ability. Moreover, the proposed hybrid FxNLMS and CNN-LSTM multi-channel network is more effective at attenuating time-varying noise than the conventional single filter network. Meanwhile, it offers superior noise reduction and real-time tracking performance compared to the deep ANC network. And compared to the conventional delay compensation method, the proposed phase tracking filter demonstrates a smaller statistical average phase error. Furthermore, simulations using recorded noise in a rehabilitation room model illustrate the efficiency of the proposed method.
- 3 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (10) , 18106-18114
Concentric Circular Nested Array Design Method for Acoustic Imaging Based on Differential Coarray Model
Acoustic imaging intuitively illustrates the locations of sound sources and has a wide range of applications, including fault detection. However, this technology requires a substantial number of microphones, which increases the complexity and cost of the data acquisition system. To reduce the number of microphones while maintaining the performance of acoustic imaging, this article introduces a concentric circular nested array (CCNA) design method. By extending the array using a differential coarray model, a virtual uniform concentric circular array is achieved. This virtual array preserves the advantages of the circular array structure while minimizing the number of required microphones. The performance of the proposed array is validated through simulation experiments. The simulation results demonstrate that the CCNA offers higher resolution, a greater dynamic range (DR), and improved positioning accuracy in acoustic imaging compared to other arrays. Finally, this article compares the acoustic imaging results of the CCNA with those of the uniform circular array (UCA) through experiments. The experimental results reveal that the positioning accuracy of the proposed CCNA surpasses that of the UCA, thereby confirming the superiority of the proposed design.
- 3 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (10) , 18106-18114
Concentric Circular Nested Array Design Method for Acoustic Imaging Based on Differential Coarray Model
Acoustic imaging intuitively illustrates the locations of sound sources and has a wide range of applications, including fault detection. However, this technology requires a substantial number of microphones, which increases the complexity and cost of the data acquisition system. To reduce the number of microphones while maintaining the performance of acoustic imaging, this article introduces a concentric circular nested array (CCNA) design method. By extending the array using a differential coarray model, a virtual uniform concentric circular array is achieved. This virtual array preserves the advantages of the circular array structure while minimizing the number of required microphones. The performance of the proposed array is validated through simulation experiments. The simulation results demonstrate that the CCNA offers higher resolution, a greater dynamic range (DR), and improved positioning accuracy in acoustic imaging compared to other arrays. Finally, this article compares the acoustic imaging results of the CCNA with those of the uniform circular array (UCA) through experiments. The experimental results reveal that the positioning accuracy of the proposed CCNA surpasses that of the UCA, thereby confirming the superiority of the proposed design.
- 27 November 2024
- Published by Elsevier in Applied Soft Computing
- Vol. 169
Enhancing robust acoustic DOA estimation against position errors via fast sparse Bayesian learning
- 27 November 2024
- Published by Elsevier in Applied Soft Computing
- Vol. 169
Enhancing robust acoustic DOA estimation against position errors via fast sparse Bayesian learning
- 19 December 2023
- Published by Elsevier in Signal Processing
- Vol. 218
Approximating the zero-norm penalized sparse signal recovery using a hierarchical Bayesian framework
- 19 December 2023
- Published by Elsevier in Signal Processing
- Vol. 218
Approximating the zero-norm penalized sparse signal recovery using a hierarchical Bayesian framework
- 19 May 2023
- Published by Springer Nature in Computational Statistics
- Vol. 38 (4) , 2053-2074
Sparse Bayesian learning with automatic-weighting Laplace priors for sparse signal recovery
- 19 May 2023
- Published by Springer Nature in Computational Statistics
- Vol. 38 (4) , 2053-2074
Sparse Bayesian learning with automatic-weighting Laplace priors for sparse signal recovery
- Open Access
- 13 December 2022
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 17 (3)
Space alternating variational estimation based sparse Bayesian learning for complex‐value sparse signal recovery using adaptive Laplace priors
Due to its self‐regularising nature and its ability to quantify uncertainty, the Bayesian approach has achieved excellent recovery performance across a wide range of sparse signal recovery applications. However, most existing methods are based on the real‐value signal model, with the complex‐value signal model rarely considered. Motivated by the adaptive least absolute shrinkage and selection operator (LASSO) and the sparse Bayesian learning framework, a hierarchical model with adaptive Laplace priors is proposed in this paper for recovery of complex sparse signals. Moreover, the space alternating approach is integrated into the algorithm to reduce the computational complexity of the proposed method. In experiments, the proposed algorithm is studied for complex Gaussian random dictionaries and different types of complex signals. These experiments show that the proposed algorithm offers better recovery performance for different types of complex signals than state‐of‐the‐art methods.
- 13 December 2022
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 17 (3)
Open AccessSpace alternating variational estimation based sparse Bayesian learning for complex‐value sparse signal recovery using adaptive Laplace priors
Due to its self‐regularising nature and its ability to quantify uncertainty, the Bayesian approach has achieved excellent recovery performance across a wide range of sparse signal recovery applications. However, most existing methods are based on the real‐value signal model, with the complex‐value signal model rarely considered. Motivated by the adaptive least absolute shrinkage and selection operator (LASSO) and the sparse Bayesian learning framework, a hierarchical model with adaptive Laplace priors is proposed in this paper for recovery of complex sparse signals. Moreover, the space alternating approach is integrated into the algorithm to reduce the computational complexity of the proposed method. In experiments, the proposed algorithm is studied for complex Gaussian random dictionaries and different types of complex signals. These experiments show that the proposed algorithm offers better recovery performance for different types of complex signals than state‐of‐the‐art methods.
- Open Access
- 6 April 2021
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2021 (1) , 1-19
Acoustic DOA estimation using space alternating sparse Bayesian learning
Estimating the direction-of-arrival (DOA) of multiple acoustic sources is one of the key technologies for humanoid robots and drones. However, it is a most challenging problem due to a number of factors, including the platform size which puts a constraint on the array aperture. To overcome this problem, a high-resolution DOA estimation algorithm based on sparse Bayesian learning is proposed in this paper. A group sparse prior based hierarchical Bayesian model is introduced to encourage spatial sparsity of acoustic sources. To obtain approximate posteriors of the hidden variables, a variational Bayesian approach is proposed. Moreover, to reduce the computational complexity, the space alternating approach is applied to push the variational Bayesian inference to the scalar level. Furthermore, an acoustic DOA estimator is proposed to jointly utilize the estimated source signals from all frequency bins. Compared to state-of-the-art approaches, the high-resolution performance of the proposed approach is demonstrated in experiments with both synthetic and real data. The experiments show that the proposed approach achieves lower root mean square error (RMSE), false alert (FA), and miss-detection (MD) than other methods. Therefore, the proposed approach can be applied to some applications such as humanoid robots and drones to improve the resolution performance for acoustic DOA estimation especially when the size of the array aperture is constrained by the platform, preventing the use of traditional methods to resolve multiple sources.
- 6 April 2021
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2021 (1) , 1-19
Open AccessAcoustic DOA estimation using space alternating sparse Bayesian learning
Estimating the direction-of-arrival (DOA) of multiple acoustic sources is one of the key technologies for humanoid robots and drones. However, it is a most challenging problem due to a number of factors, including the platform size which puts a constraint on the array aperture. To overcome this problem, a high-resolution DOA estimation algorithm based on sparse Bayesian learning is proposed in this paper. A group sparse prior based hierarchical Bayesian model is introduced to encourage spatial sparsity of acoustic sources. To obtain approximate posteriors of the hidden variables, a variational Bayesian approach is proposed. Moreover, to reduce the computational complexity, the space alternating approach is applied to push the variational Bayesian inference to the scalar level. Furthermore, an acoustic DOA estimator is proposed to jointly utilize the estimated source signals from all frequency bins. Compared to state-of-the-art approaches, the high-resolution performance of the proposed approach is demonstrated in experiments with both synthetic and real data. The experiments show that the proposed approach achieves lower root mean square error (RMSE), false alert (FA), and miss-detection (MD) than other methods. Therefore, the proposed approach can be applied to some applications such as humanoid robots and drones to improve the resolution performance for acoustic DOA estimation especially when the size of the array aperture is constrained by the platform, preventing the use of traditional methods to resolve multiple sources.